Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    statements involving opinions or judgments on race and morality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bels
    -0.44
     initial
    -0.39
    </i>
    -0.38
     
    -0.38
     initially
    -0.37
    록
    -0.37
     плане
    -0.36
     بگیرید
    -0.36
     flu
    -0.35
     Flu
    -0.35
    POSITIVE LOGITS
    Hozzáférés
    0.88
     oprot
    0.85
     HasFactory
    0.85
    SizeMode
    0.82
    WebVitals
    0.82
     autorytatywna
    0.80
     مشين
    0.79
     виправивши
    0.79
     kaarangay
    0.74
    :✨
    0.74
    Act Density 0.189%

    No Known Activations